In this digital era, Wireless Sensor networks (WSN), or else, Internet of Things (IoT) when these sensor networks are accessible via the internet, is a common and widely used technology. These tiny sensor nodes in these networks help to enhance and automate processes in various fields such as, smart homes and cities, healthcare, smart vehicular networks, Smart Grids and so on. Although this technology is widely used in many fields, these tiny devices are equipped with limited amounts of resources. Limited capacity of battery power is one of the major concerns with IoT when it comes to some specific applications. In addition to this, this limited battery capacity is vulnerable for power depletion attacks which can reduce the lifetime of these devices significantly. So, there is an urgent need of solid solution to preserve this battery power as much as possible. One proper solution for this is, a machine learning based intelligent intrusion detection system that can detect power depletion attacks against these IoT applications. However, the lack of a proper dataset to train and evaluate these machine learning models appears as a major obstacle for an intelligent intrusion detection system. So, in this paper, we are going to discuss how we can use COOJA simulator to generate a proper dataset that can be used to develop and evaluate machine learning models to detect Denial of Sleep attacks against Wireless Sensor Networks. Here, we are going to discuss 3 strategies (UDP flood attack, wormhole attack and externally generated legitimate request attack) to simulate Denial of Sleep attacks for WSNs, so that, any person can generate their own dataset according to their requirements. At the end of the paper, we have evaluated each strategy to deplete the power of the sensor nodes. Then, our conclusions are given.

The Internet of Things (IoT) has rapidly evolved into a central component of today’s technological landscape, enabling seamless connectivity and communication among a vast array of devices. It underpins automation, real-time monitoring, and smart infrastructure, serving as a foundation for Industry 4.0 and paving the way toward Industry 5.0. Despite the potential of IoT systems to transform industries, these systems face a number of challenges, most notably the lack of processing power, storage space, and battery life. Whereas cloud and fog computing help to relieve computational and storage constraints, energy limitations remain a severe impediment to long-term autonomous operation. Among the threats that exploit this weakness, the Denial-of-Sleep (DoSl) attack is particularly problematic because it prevents nodes from entering low-power states, leading to battery depletion and degraded network performance. This research investigates machine-learning (ML) and deep-learning (DL) methods for identifying such energy-wasting behaviors to protect IoT energy resources. A dataset was generated in a simulated IoT environment under multiple DoSl attack conditions to validate the proposed approach. Several ML and DL models were trained and tested on this data to discover distinctive power-consumption patterns related to the attacks. The experimental results confirm that the proposed models can effectively detect anomalous behaviors associated with DoSl activity, demonstrating their potential for energy-aware threat detection in IoT networks. Specifically, the Random Forest and Decision Tree classifiers achieved accuracies of 98.57% and 97.86%, respectively, on the held-out 25% test set, while the Long Short-Term Memory (LSTM) model reached 97.92% accuracy under a chronological split, confirming effective temporal generalization. All evaluations were conducted in a simulated environment, and the paper also outlines potential pathways for future physical testbed deployment.